No-reference image quality assessment through transfer learning

Feng, Yeli; Cai, Yiyu

doi:10.1109/siprocess.2017.8124512

Cited by 9 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, there are few works on quality evaluation based on transfer learning. A transfer learning framework was described in [30], which learned an end-to-end image quality estimator in classification or regression. In [31], the features extracted from distorted images were transferred to the same feature space, in order to solve the problem of insufficient video contents.…”

Section: B Transfer Learning and Object Detectionmentioning

confidence: 99%

Utility-Oriented Underwater Image Quality Assessment Based on Transfer Learning

Chen¹,

Lin²,

Liao³

et al. 2022

Preprint

View full text Add to dashboard Cite

The widespread image applications have greatly promoted the vision-based tasks, in which the Image Quality Assessment (IQA) technique has become an increasingly significant issue. For user enjoyment in multimedia systems, the IQA exploits image fidelity and aesthetics to characterize user experience; while for other tasks such as popular object recognition, there exists a low correlation between utilities and perceptions. In such cases, the fidelity-based and aesthetics-based IQA methods cannot be directly applied. To address this issue, this paper proposes a utility-oriented IQA in object recognition.In particular, we initialize our research in the scenario of underwater fish detection, which is a critical task that has not yet been perfectly addressed. Based on this task, we build an Underwater Image Utility Database (UIUD) and a learningbased Underwater Image Utility Measure (UIUM). Inspired by the top-down design of fidelity-based IQA, we exploit the deep models of object recognition and transfer their features to our UIUM. Experiments validate that the proposed transfer-learningbased UIUM achieves promising performance in the recognition task. We envision our research provides insights to bridge the researches of IQA and computer vision.

show abstract

Section: B Transfer Learning and Object Detectionmentioning

confidence: 99%

Utility-Oriented Underwater Image Quality Assessment Based on Transfer Learning

Chen¹,

Lin²,

Liao³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In this study, we use a learning-based no-reference IQA algorithm DTNIQ-f by Feng et al [120] to obtain the visual quality score of distorted and adversarial images. For investigation, we collect 4966 distorted or pristine images from the traditional image quality research literature, 5000 unrecognizable fooling images from [106]; using color images from ImageNet validation set and the universal perturbation [125] method produces 49,056 recognizable adversarial images, and using gradient ascent method produces 3000 unrecognizable adversarial images.…”

Section: Methodsmentioning

confidence: 99%

“…In the meantime, studies [116][117][118][119][120][121][122][123][124][125][126][127] discover that deep neural networks can give surprisingly egregious outputs given artificially crafted fooling images or images injected with malicious changes that are hardly perceivable by the human visual system. Such Today, artificial intelligence dominates the news headlines, promises enormous potential benefits to businesses and society.…”

Section: Background and Motivationmentioning

confidence: 99%